IP Library Granted Patent US 12,614,271
Granted Patent B2
US 12,614,271 · App. 18/554,612 · Granted Apr 28, 2026

Polarization image-based building inspection

Inventors: Caitlin M. Race (Stillwater, MN); Patrick S. Bowden (Minneapolis, MN); Nathaniel D. Anderson (Stillwater, MN); Paul A. Kendrick (North Oaks, MN); Orlin B. Knudson (Vadnais Heights, MN); Jonah Shaver (Stillwater, MN)
Assignee: 3M Innovative Properties Company
G06T7/0004G06T7/11G06V10/764G06T2207/20084G06T2207/30124G06T2207/30184G06V2201/07
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,614,271
App. No.
18/554,612
Granted
Apr 28, 2026
Kind
B2
Abstract

Systems of this disclosure enable building inspection using polarization images. The systems use light polarization information of the polarization images to detect misapplications of tape applied to a substrate. An example system includes polarization camera hardware, a memory communicatively coupled to the polarization camera hardware, and processing circuitry communicatively coupled to the memory. The polarization camera hardware is configured to capture a polarization image of a tape as applied to a substrate. The memory is configured to store the polarization image. The processing circuitry is configured to analyze the polarization image according to a trained classification model and, based on the analysis of the polarization image according to the trained classification model, detect a misapplication with respect to the tape as applied to the substrate.

Claims (30)

1 . A system comprising:

polarization camera hardware configured to capture a polarization image of a tape as applied to an envelope layer of a building;

a memory communicatively coupled to the polarization camera hardware, the memory being configured to store the polarization image; and

processing circuitry communicatively coupled to the memory, the processing circuitry being configured to:

analyze the polarization image according to a trained classification model; and

based on the analysis of the polarization image according to the trained classification model, detect a misapplication with respect to the tape as applied to the envelope layer of the building, the misapplication being associated with at least one of a fishmouth crease or a crease in the tape as applied to the envelope layer of the building.

2 . The system of claim 1 , wherein the trained classification model is a trained neural network model.

3 . The system of claim 1 , wherein the polarization camera hardware is integrated into a mobile computing device.

4 . The system of claim 1 , wherein the polarization camera hardware is communicatively coupled to a mobile computing device.

5 . The system of claim 3 , wherein the mobile computing device comprises one of a smartphone, a tablet computer, or a wearable computing device.

6 . The system of claim 1 , wherein the polarization camera hardware is communicatively coupled to a drone.

7 . The system of claim 1 , wherein the polarization camera hardware is integrated into a drone.

8 . The system of claim 1 , further comprising output hardware communicatively coupled to the processing circuitry, wherein the processing circuitry is further configured to output, via the output hardware, a model output indicative of the misapplication of the tape as applied to the envelope layer of the building.

9 . The system of claim 1 , wherein the trained classification model is configured to implement one or more of full-image classification, sub-image classification, object detection, or image segmentation with respect to the polarization image.

10 . The system of claim 1 , wherein the polarization image indicates division of focal plane (DoLP) data with respect to the tape as applied to the envelope layer of the building.

11 . A method comprising:

capturing, by polarization camera hardware, a polarization image of a tape as applied to an envelope layer of a building;

analyzing, by processing circuitry communicatively coupled to the image capture hardware, the polarization image according to a trained classification model; and

detecting, by the processing circuitry, based on the analysis of the polarization image according to the trained classification model, a misapplication with respect to the tape as applied to the envelope layer of the building, the misapplication being associated with at least one of a fishmouth crease or a crease in the tape as applied to the envelope layer of the building.

12 . The method of claim 11 , wherein the trained model is a trained neural network model.

13 . The method of claim 11 , wherein the polarization camera hardware is integrated into a mobile computing device.

14 . The method of claim 11 , wherein the polarization camera hardware is integrated into a drone.

15 . The method of claim 11 , further comprising outputting, by the processing circuitry, via output hardware communicatively coupled to the processing circuitry, a model output indicative of the misapplication of the tape as applied to the envelope layer of the building.

16 . The method of claim 11 , wherein the trained model is configured to implement one or more of full-image classification, sub-image classification, object detection, or image segmentation with respect to the polarization image.

17 . The method of claim 11 , wherein the polarization image indicates division of focal plane (DoLP) data with respect to the tape as applied to the envelope layer of the building.

18 . A computer-readable storage device encoded with instructions that, when executed, cause processing circuitry of a computing device to:

receive, from polarization camera hardware, a polarization image of a tape as applied to an envelope layer of a building;

store the polarization image to the computer-readable storage device;

analyze the polarization image according to a trained model; and

based on the analysis of the polarization image according to the trained model, detect a misapplication with respect to the tape as applied to the envelope layer of the building, the misapplication being associated with at least one of a fishmouth crease or a crease in the tape as applied to the envelope layer of the building.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 9, 2023
From: RACE, CAITLIN M.; BOWDEN, PATRICK S.; ANDERSON, NATHANIEL D.; KENDRICK, PAUL A.; KNUDSON, ORLIN B.; SHAVER, JONAH
To: 3M INNOVATIVE PROPERTIES COMPANY
Reel/Frame 065163/0280 →
Continuity (2)
Provisional Application 63201095 · Apr 12, 2021
Related Publication 20240221144A1 · Jul 4, 2024
References Cited (40)
US 11199689B2 · Krueger et al. · 2021 [cited by applicant]
US 20130139953A1 · Galush et al. · 2013 [cited by applicant]
US 20140147611A1 · Ackerman, Jr. · 2014 [cited by examiner]
US 20190031923A1 · Khurana et al. · 2019 [cited by applicant]
US 20200003098A1 · Okajima et al. · 2020 [cited by applicant]
US 20200166938A1 · Hafenrichter · 2020 [cited by applicant]
US 20200410209A1 · Zass · 2020 [cited by examiner]
US 20210004948A1 · Zass · 2021 [cited by applicant]
US 20230048725A1 · Barbour · 2023 [cited by examiner]
CN 108388907B · 2021 [cited by applicant]
CN 107491734B · 2021 [cited by applicant]
CN 107340546B · 2023 [cited by applicant]
EP 0330495A2 · 1989 [cited by examiner]
EP 3598194A1 · 2020 [cited by applicant]
JP 2002055055A · 2002 [cited by examiner]
JP 2014035183A · 2014 [cited by applicant]
JP 2018017103A · 2018 [cited by applicant]
JP 2020065330A · 2020 [cited by applicant]
JP 2021056144A · 2021 [cited by applicant]
WO 2014031615A1 · 2014 [cited by applicant]
WO 2015126931A1 · 2015 [cited by applicant]
WO 2015183354A2 · 2015 [cited by applicant]
WO 2016019248A1 · 2016 [cited by applicant]
WO 2016106273A1 · 2016 [cited by applicant]
WO 2017031275A1 · 2017 [cited by applicant]
WO 2017112756A1 · 2017 [cited by applicant]
WO 2018156631A1 · 2018 [cited by applicant]
WO 2018220555A1 · 2018 [cited by applicant]
WO 2019089049A1 · 2019 [cited by applicant]
WO 2019152621A1 · 2019 [cited by applicant]
WO 2020003150A2 · 2020 [cited by applicant]
WO 2021024206A1 · 2021 [cited by applicant]
WO 2021033061A1 · 2021 [cited by applicant]
WO 2021033111A1 · 2021 [cited by applicant]
WO WO2021067665A2 · 2021 [cited by examiner]
WO 2022219472A1 · 2022 [cited by applicant]
Extended European Search Report, EP 22787720, Jan. 14, 2025, 2 pages. [cited by applicant]
International Search Report received for PCT International Application No. PCT/IB2022/053293, mailed on Jun. 27, 2022, 2 pages. [cited by applicant]
Jones, “Physics 42200: Waves & Oscillations—Lecture 28—Polarization of Light”, 2013, Department of Physics, Purdue University, 25 pages. [cited by applicant]
Teledyne Flir, “Save Time and Effort with On-Sensor Polarization”, URL: <https://www.flir.com/discover/iis/machine-vision/imaging-reflective-surfaces-sonys-first-polarized-sensor/>, Jan. 28, 2022, 13 pages. [cited by applicant]